// MCP TOOL REFERENCE

CROSS-LLM MCP SERVER TOOLS

23 tools from the Cross-LLM MCP Server MCP Server, categorised by risk level.

// ALL 23 CROSS-LLM MCP SERVER TOOLS

READ 7 tools

Read get-async-job-result Get the status and result of an async LLM job by job ID Read get-model-registry-info Get information about the model registry including the last updated timestamp Read get-models-by-tag Get all models matching a specific tag (coding, business, reasoning, math, creative, general) Read get-prompt-history Get history of prompts sent to LLMs with optional filters Read get-prompt-stats Get statistics about prompt logs (total entries, by provider, by model, token usage, etc.) Read get-user-preferences Get current user preferences including default model and cost preference Read list-async-jobs List async jobs with optional filters (status, provider, limit)

WRITE 2 tools

Write cancel-async-job Cancel a pending or processing async job Write set-user-preferences Set user preferences for default model, cost preference, and tag-based model preferences (e.g., use deepsee...

DESTRUCTIVE 2 tools

Destructive clear-prompt-history Clear all prompt log entries Destructive delete-prompt-entries Delete prompt log entries matching specified criteria

EXECUTE 12 tools

Execute call-all-llms Call all available LLM APIs (ChatGPT, Claude, DeepSeek, Gemini, Grok, Kimi, Perplexity, Mistral, Hugging Fa... Execute call-chatgpt Call OpenAI Execute call-claude Call Anthropic Execute call-deepseek Call DeepSeek API with a prompt Execute call-gemini Call Google Execute call-grok Call xAI Execute call-huggingface Call Hugging Face Inference Router (OpenAI-compatible chat completions) with a prompt Execute call-kimi Call Moonshot AI Execute call-llm Call a specific LLM provider by name Execute call-mistral Call Mistral AI Execute call-perplexity Call Perplexity AI Execute submit-llm-request-async Submit an LLM request to be processed asynchronously. Returns a job ID immediately that can be used to poll...

// FAQ

How many tools does the Cross-LLM MCP Server MCP server have? +

The Cross-LLM MCP Server MCP server exposes 23 tools across 4 categories: Read, Write, Destructive, Execute.

How do I enforce policies on Cross-LLM MCP Server tools? +

Route the Cross-LLM MCP Server server through the PolicyLayer gateway. Define allow, deny, or approval rules per tool in the dashboard; they are enforced on every call before it reaches the server.

What risk categories do Cross-LLM MCP Server tools fall into? +

Cross-LLM MCP Server tools are categorised as Read (7), Write (2), Destructive (2), Execute (12). Each category has a recommended default policy.

Enforce policy on every Cross-LLM MCP Server tool call.

Start from Cross-LLM MCP Server, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.

CHECK YOUR STACK →

Free to start. No card required.

43,000+ MCP servers and 220,000+ tools scanned and risk-classified.